135 citations · 330 across the 11 of their papers we have counts for
11 papers
On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
Mohammed Fellaji, Frédéric Pennerath, Brieuc Conan-Guez +1
The calibration of predictive distributions has been widely studied in deep learning, but the same cannot be said about the more specific epistemic uncertainty as produced by Deep…
Clarity: an improved gradient method for producing quality visual counterfactual explanations
Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez +2
Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (V…
A Bayesian Convolutional Neural Network for Robust Galaxy Ellipticity Regression
Claire Theobald, Bastien Arcelin, Frédéric Pennerath +3
Cosmic shear estimation is an essential scientific goal for large galaxy surveys. It refers to the coherent distortion of distant galaxy images due to weak gravitational lensing al…
A Bayesian Neural Network based on Dropout Regulation
Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez +2
Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application do…
Dissimilarity Clustering by Hierarchical Multi-Level Refinement
Brieuc Conan-Guez, Fabrice Rossi
We introduce in this paper a new way of optimizing the natural extension of the quantization error using in k-means clustering to dissimilarity data. The proposed method is based o…
Multi-Layer Perceptrons and Symbolic Data
Fabrice Rossi, Brieuc Conan-Guez
In some real world situations, linear models are not sufficient to represent accurately complex relations between input variables and output variables of a studied system. Multilay…